{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T05:54:24Z","timestamp":1757310864257,"version":"3.37.3"},"reference-count":64,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,5,15]],"date-time":"2024-05-15T00:00:00Z","timestamp":1715731200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,5,15]],"date-time":"2024-05-15T00:00:00Z","timestamp":1715731200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100010613","name":"Taipei Medical University Hospital","doi-asserted-by":"publisher","award":["111TMU-TMUH-13"],"award-info":[{"award-number":["111TMU-TMUH-13"]}],"id":[{"id":"10.13039\/501100010613","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100010002","name":"Ministry of Education","doi-asserted-by":"publisher","award":["Higher Education Sprout Project"],"award-info":[{"award-number":["Higher Education Sprout Project"]}],"id":[{"id":"10.13039\/100010002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Eur Radiol Exp"],"abstract":"<jats:title>Abstract<\/jats:title><jats:sec>\n                <jats:title>Background<\/jats:title>\n                <jats:p>This study investigates the potential of diffusion tensor imaging (DTI) in identifying penumbral volume (PV) compared to the standard gadolinium-required perfusion\u2013diffusion mismatch (PDM), utilizing a stack-based ensemble machine learning (ML) approach with enhanced explainability.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Methods<\/jats:title>\n                <jats:p>Sixteen male rats were subjected to middle cerebral artery occlusion. The penumbra was identified using PDM at 30 and 90\u00a0min after occlusion. We used 11 DTI-derived metrics and 14 distance-based features to train five voxel-wise ML models. The model predictions were integrated using stack-based ensemble techniques. ML-estimated and PDM-defined PVs were compared to evaluate model performance through volume similarity assessment, the Pearson correlation analysis, and Bland\u2013Altman analysis. Feature importance was determined for explainability.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Results<\/jats:title>\n                <jats:p>In the test rats, the ML-estimated median PV was 106.4\u00a0mL (interquartile range 44.6\u2013157.3\u00a0mL), whereas the PDM-defined median PV was 102.0\u00a0mL (52.1\u2013144.9\u00a0mL). These PVs had a volume similarity of 0.88 (0.79\u20130.96), a Pearson correlation coefficient of 0.93 (<jats:italic>p<\/jats:italic>\u2009&lt;\u20090.001), and a Bland\u2013Altman bias of 2.5\u00a0mL (2.4% of the mean PDM-defined PV), with 95% limits of agreement ranging from\u2009-44.9 to 49.9\u00a0mL. Among the features used for PV prediction, the mean diffusivity was the most important feature.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Conclusions<\/jats:title>\n                <jats:p>Our study confirmed that PV can be estimated using DTI metrics with a stack-based ensemble ML approach, yielding results comparable to the volume defined by the standard PDM. The model explainability enhanced its clinical relevance. Human studies are warranted to validate our findings.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Relevance statement<\/jats:title>\n                <jats:p>The proposed DTI-based ML model can estimate PV without the need for contrast agent administration, offering a valuable option for patients with kidney dysfunction. It also can serve as an alternative if perfusion map interpretation fails in the clinical setting.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Key points<\/jats:title>\n                <jats:p>\u2022 Penumbral volume can be estimated by DTI combined with stack-based ensemble ML.<\/jats:p>\n                <jats:p>\u2022 Mean diffusivity was the most important feature used for predicting penumbral volume.<\/jats:p>\n                <jats:p>\u2022 The proposed approach can be beneficial for patients with kidney dysfunction.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Graphical Abstract<\/jats:title>\n                \n              <\/jats:sec>","DOI":"10.1186\/s41747-024-00455-z","type":"journal-article","created":{"date-parts":[[2024,5,15]],"date-time":"2024-05-15T00:01:49Z","timestamp":1715731309000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Estimating the volume of penumbra in rodents using DTI and stack-based ensemble machine learning framework"],"prefix":"10.1186","volume":"8","author":[{"given":"Duen-Pang","family":"Kuo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0333-428X","authenticated-orcid":false,"given":"Yung-Chieh","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi-Tien","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sho-Jen","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kevin Li-Chun","family":"Hsieh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Po-Chih","family":"Kuo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chen-Yin","family":"Ou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cheng-Yu","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,5,15]]},"reference":[{"key":"455_CR1","doi-asserted-by":"publisher","first-page":"131","DOI":"10.5853\/jos.2014.16.3.131","volume":"16","author":"BJ Kim","year":"2014","unstructured":"Kim BJ, Kang HG, Kim HJ et al (2014) Magnetic resonance imaging in acute ischemic stroke treatment. J Stroke 16:131\u2013145. https:\/\/doi.org\/10.5853\/jos.2014.16.3.131","journal-title":"J Stroke"},{"key":"455_CR2","doi-asserted-by":"publisher","first-page":"611","DOI":"10.1056\/NEJMoa1804355","volume":"379","author":"G Thomalla","year":"2018","unstructured":"Thomalla G, Simonsen CZ, Boutitie F et al (2018) Mri-guided thrombolysis for stroke with unknown time of onset. N Engl J Med 379:611\u2013622. https:\/\/doi.org\/10.1056\/NEJMoa1804355","journal-title":"N Engl J Med"},{"key":"455_CR3","doi-asserted-by":"publisher","first-page":"3439","DOI":"10.1161\/strokeaha.121.038101","volume":"53","author":"D Reyes","year":"2022","unstructured":"Reyes D, Simpkins AN, Hitomi E et al (2022) Estimating perfusion deficits in acute stroke patients without perfusion imaging. Stroke 53:3439\u20133445. https:\/\/doi.org\/10.1161\/strokeaha.121.038101","journal-title":"Stroke"},{"key":"455_CR4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.pnmrs.2013.04.002","volume":"74","author":"F Calamante","year":"2013","unstructured":"Calamante F (2013) Arterial input function in perfusion mri: a comprehensive review. Prog Nucl Magn Reson Spectrosc 74:1\u201332. https:\/\/doi.org\/10.1016\/j.pnmrs.2013.04.002","journal-title":"Prog Nucl Magn Reson Spectrosc"},{"key":"455_CR5","doi-asserted-by":"publisher","first-page":"129","DOI":"10.3988\/jcn.2018.14.2.129","volume":"14","author":"WS Tae","year":"2018","unstructured":"Tae WS, Ham BJ, Pyun SB et al (2018) Current clinical applications of diffusion-tensor imaging in neurological disorders. J Clin Neurol 14:129\u2013140. https:\/\/doi.org\/10.3988\/jcn.2018.14.2.129","journal-title":"J Clin Neurol"},{"key":"455_CR6","doi-asserted-by":"publisher","first-page":"1327","DOI":"10.2214\/AJR.12.9816","volume":"200","author":"KA Cauley","year":"2013","unstructured":"Cauley KA, Thangasamy S, Dundamadappa SK (2013) Improved image quality and detection of small cerebral infarctions with diffusion-tensor trace imaging. AJR Am J Roentgenol 200:1327\u20131333. https:\/\/doi.org\/10.2214\/AJR.12.9816","journal-title":"AJR Am J Roentgenol"},{"key":"455_CR7","doi-asserted-by":"publisher","first-page":"491","DOI":"10.1007\/s00221-010-2496-8","volume":"208","author":"M Urbanski","year":"2011","unstructured":"Urbanski M, Thiebaut de Schotten M, Rodrigo S et al (2011) DTI-MR tractography of white matter damage in stroke patients with neglect. Exp Brain Res 208:491\u2013505. https:\/\/doi.org\/10.1007\/s00221-010-2496-8","journal-title":"Exp Brain Res"},{"key":"455_CR8","doi-asserted-by":"publisher","first-page":"269","DOI":"10.3348\/kjr.2017.18.2.269","volume":"18","author":"DP Kuo","year":"2017","unstructured":"Kuo DP, Lu CF, Liou M et al (2017) Differentiation of the infarct core from ischemic penumbra within the first 4.5 hours, using diffusion tensor imaging-derived metrics: a rat model. Korean J Radiol 18:269\u2013278. https:\/\/doi.org\/10.3348\/kjr.2017.18.2.269","journal-title":"Korean J Radiol"},{"key":"455_CR9","doi-asserted-by":"publisher","first-page":"1162","DOI":"10.1161\/STROKEAHA.111.678110","volume":"44","author":"J Puig","year":"2013","unstructured":"Puig J, Blasco G, Daunis IEJ et al (2013) Increased corticospinal tract fractional anisotropy can discriminate stroke onset within the first 4.5 hours. Stroke 44:1162\u20131165. https:\/\/doi.org\/10.1161\/STROKEAHA.111.678110","journal-title":"Stroke"},{"key":"455_CR10","doi-asserted-by":"publisher","first-page":"1161","DOI":"10.3348\/kjr.2018.19.6.1161","volume":"19","author":"FY Chiu","year":"2018","unstructured":"Chiu FY, Kuo DP, Chen YC et al (2018) Diffusion tensor-derived properties of benign oligemia, true \u201cat risk\u201d penumbra, and infarct core during the first three hours of stroke onset: A rat model. Korean J Radiol 19:1161\u20131171. https:\/\/doi.org\/10.3348\/kjr.2018.19.6.1161","journal-title":"Korean J Radiol"},{"key":"455_CR11","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1109\/Mci.2015.2471235","volume":"11","author":"Y Ren","year":"2016","unstructured":"Ren Y, Zhang L, Suganthan PN (2016) Ensemble classification and regression-recent developments, applications and future directions. IEEE Comput Intell Mag 11:41\u201353. https:\/\/doi.org\/10.1109\/Mci.2015.2471235","journal-title":"IEEE Comput Intell Mag"},{"key":"455_CR12","doi-asserted-by":"publisher","first-page":"255","DOI":"10.1023\/B:MACH.0000015881.36452.6e","volume":"54","author":"S D\u017eeroski","year":"2004","unstructured":"D\u017eeroski S, \u017denko B (2004) Is combining classifiers with stacking better than selecting the best one? Mach Learn 54:255\u2013273. https:\/\/doi.org\/10.1023\/B:MACH.0000015881.36452.6e","journal-title":"Mach Learn"},{"key":"455_CR13","doi-asserted-by":"publisher","first-page":"188","DOI":"10.1016\/j.asoc.2019.01.015","volume":"77","author":"Y Wang","year":"2019","unstructured":"Wang Y, Wang D, Geng N et al (2019) Stacking-based ensemble learning of decision trees for interpretable prostate cancer detection. Appl Soft Comput 77:188\u2013204. https:\/\/doi.org\/10.1016\/j.asoc.2019.01.015","journal-title":"Appl Soft Comput"},{"key":"455_CR14","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1161\/01.str.20.1.84","volume":"20","author":"EZ Longa","year":"1989","unstructured":"Longa EZ, Weinstein PR, Carlson S et al (1989) Reversible middle cerebral artery occlusion without craniectomy in rats. Stroke 20:84\u201391. https:\/\/doi.org\/10.1161\/01.str.20.1.84","journal-title":"Stroke"},{"key":"455_CR15","doi-asserted-by":"publisher","first-page":"207","DOI":"10.1002\/ana.10803","volume":"55","author":"X Meng","year":"2004","unstructured":"Meng X, Fisher M, Shen Q et al (2004) Characterizing the diffusion\/perfusion mismatch in experimental focal cerebral ischemia. Ann Neurol 55:207\u2013212. https:\/\/doi.org\/10.1002\/ana.10803","journal-title":"Ann Neurol"},{"key":"455_CR16","doi-asserted-by":"publisher","first-page":"S208","DOI":"10.1016\/j.neuroimage.2004.07.051","volume":"23 Suppl 1","author":"SM Smith","year":"2004","unstructured":"Smith SM, Jenkinson M, Woolrich MW et al (2004) Advances in functional and structural mr image analysis and implementation as fsl. Neuroimage 23 Suppl 1:S208\u2013219. https:\/\/doi.org\/10.1016\/j.neuroimage.2004.07.051","journal-title":"Neuroimage"},{"key":"455_CR17","doi-asserted-by":"publisher","first-page":"1146","DOI":"10.1161\/01.str.0000014208.05597.33","volume":"33","author":"F Calamante","year":"2002","unstructured":"Calamante F, Gadian DG, Connelly A (2002) Quantification of perfusion using bolus tracking magnetic resonance imaging in stroke: assumptions, limitations, and potential implications for clinical use. Stroke 33:1146\u20131151. https:\/\/doi.org\/10.1161\/01.str.0000014208.05597.33","journal-title":"Stroke"},{"key":"455_CR18","doi-asserted-by":"publisher","first-page":"1112","DOI":"10.1007\/s00330-012-2688-7","volume":"23","author":"D Cortez-Conradis","year":"2013","unstructured":"Cortez-Conradis D, Favila R, Isaac-Olive K et al (2013) Diagnostic performance of regional dti-derived tensor metrics in glioblastoma multiforme: Simultaneous evaluation of p, q, l, cl, cp, cs, ra, rd, ad, mean diffusivity and fractional anisotropy. Eur Radiol 23:1112\u20131121. https:\/\/doi.org\/10.1007\/s00330-012-2688-7","journal-title":"Eur Radiol"},{"key":"455_CR19","doi-asserted-by":"publisher","first-page":"498","DOI":"10.3109\/03091902.2015.1094148","volume":"39","author":"A Renjith","year":"2015","unstructured":"Renjith A, Manjula P, Mohan Kumar P (2015) Brain tumour classification and abnormality detection using neuro-fuzzy technique and otsu thresholding. J Med Eng Technol 39:498\u2013507. https:\/\/doi.org\/10.3109\/03091902.2015.1094148","journal-title":"J Med Eng Technol"},{"key":"455_CR20","doi-asserted-by":"publisher","first-page":"659","DOI":"10.1016\/j.neuroimage.2009.04.070","volume":"47","author":"T Tourdias","year":"2009","unstructured":"Tourdias T, Dragonu I, Fushimi Y et al (2009) Aquaporin 4 correlates with apparent diffusion coefficient and hydrocephalus severity in the rat brain: A combined mri-histological study. Neuroimage 47:659\u2013666. https:\/\/doi.org\/10.1016\/j.neuroimage.2009.04.070","journal-title":"Neuroimage"},{"key":"455_CR21","doi-asserted-by":"publisher","first-page":"860","DOI":"10.1161\/STROKEAHA.119.027611","volume":"51","author":"H Lee","year":"2020","unstructured":"Lee H, Lee EJ, Ham S et al (2020) Machine learning approach to identify stroke within 4.5 hours. Stroke 51:860\u2013866. https:\/\/doi.org\/10.1161\/STROKEAHA.119.027611","journal-title":"Stroke"},{"key":"455_CR22","doi-asserted-by":"publisher","first-page":"887","DOI":"10.1097\/01.WCB.0000124321.60992.87","volume":"24","author":"Q Shen","year":"2004","unstructured":"Shen Q, Ren H, Fisher M et al (2004) Dynamic tracking of acute ischemic tissue fates using improved unsupervised isodata analysis of high-resolution quantitative perfusion and diffusion data. J Cereb Blood Flow Metab 24:887\u2013897. https:\/\/doi.org\/10.1097\/01.WCB.0000124321.60992.87","journal-title":"J Cereb Blood Flow Metab"},{"key":"455_CR23","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1002\/cem.2692","volume":"29","author":"RG Brereton","year":"2015","unstructured":"Brereton RG (2015) The mahalanobis distance and its relationship to principal component scores. J Chemometr 29:143\u2013145. https:\/\/doi.org\/10.1002\/cem.2692","journal-title":"J Chemometr"},{"key":"455_CR24","doi-asserted-by":"publisher","first-page":"92","DOI":"10.1016\/j.ins.2011.07.048","volume":"184","author":"SL France","year":"2012","unstructured":"France SL, Carroll JD, Xiong H (2012) Distance metrics for high dimensional nearest neighborhood recovery: compression and normalization. Inform Sciences 184:92\u2013110. https:\/\/doi.org\/10.1016\/j.ins.2011.07.048","journal-title":"Inform Sciences"},{"key":"455_CR25","doi-asserted-by":"publisher","first-page":"161","DOI":"10.4304\/jcp.7.1.161-168","volume":"7","author":"W Yang","year":"2012","unstructured":"Yang W, Wang K, Zuo W (2012) Neighborhood component feature selection for high-dimensional data. J Comput 7:161\u2013168. https:\/\/doi.org\/10.4304\/jcp.7.1.161-168","journal-title":"J Comput"},{"key":"455_CR26","doi-asserted-by":"publisher","first-page":"118","DOI":"10.1016\/j.compbiomed.2019.02.009","volume":"107","author":"NS Malan","year":"2019","unstructured":"Malan NS, Sharma S (2019) Feature selection using regularized neighbourhood component analysis to enhance the classification performance of motor imagery signals. Comput Biol Med 107:118\u2013126. https:\/\/doi.org\/10.1016\/j.compbiomed.2019.02.009","journal-title":"Comput Biol Med"},{"key":"455_CR27","doi-asserted-by":"publisher","first-page":"26","DOI":"10.9781\/ijimai.2016.415","volume":"4","author":"H Ramchoun","year":"2016","unstructured":"Ramchoun H, Ghanou Y, Ettaouil M et al (2016) Multilayer perceptron: Architecture optimization and training. Int J Interact Multimed Artif Intell 4:26\u201330. https:\/\/doi.org\/10.9781\/ijimai.2016.415","journal-title":"Int J Interact Multimed Artif Intell"},{"key":"455_CR28","doi-asserted-by":"publisher","first-page":"187","DOI":"10.1177\/096228029500400302","volume":"4","author":"T Hastie","year":"1995","unstructured":"Hastie T, Tibshirani R (1995) Generalized additive models for medical research. Stat Methods Med Res 4:187\u2013196. https:\/\/doi.org\/10.1177\/096228029500400302","journal-title":"Stat Methods Med Res"},{"key":"455_CR29","doi-asserted-by":"publisher","first-page":"275","DOI":"10.1002\/cem.873","volume":"18","author":"AJ Myles","year":"2004","unstructured":"Myles AJ, Feudale RN, Liu Y et al (2004) An introduction to decision tree modeling. J Chemometr 18:275\u2013285. https:\/\/doi.org\/10.1002\/cem.873","journal-title":"J Chemometr"},{"key":"455_CR30","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1023\/A:1007515423169","volume":"36","author":"E Bauer","year":"1999","unstructured":"Bauer E, Kohavi R (1999) An empirical comparison of voting classification algorithms: bagging, boosting, and variants. Mach Learn 36:105\u2013139. https:\/\/doi.org\/10.1023\/A:1007515423169","journal-title":"Mach Learn"},{"key":"455_CR31","doi-asserted-by":"publisher","unstructured":"Chang SC, Chu CL, Chen CK et al (2021) The comparison and interpretation of machine-learning models in post-stroke functional outcome prediction. Diagnostics (Basel) 11. https:\/\/doi.org\/10.3390\/diagnostics11101784","DOI":"10.3390\/diagnostics11101784"},{"key":"455_CR32","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1186\/s12880-015-0068-x","volume":"15","author":"AA Taha","year":"2015","unstructured":"Taha AA, Hanbury A (2015) Metrics for evaluating 3d medical image segmentation: analysis, selection, and tool. BMC Med Imaging 15:29. https:\/\/doi.org\/10.1186\/s12880-015-0068-x","journal-title":"BMC Med Imaging"},{"key":"455_CR33","doi-asserted-by":"publisher","first-page":"1700","DOI":"10.1161\/01.STR.0000173407.40773.17","volume":"36","author":"J Prosser","year":"2005","unstructured":"Prosser J, Butcher K, Allport L et al (2005) Clinical-diffusion mismatch predicts the putative penumbra with high specificity. Stroke 36:1700\u20131704. https:\/\/doi.org\/10.1161\/01.STR.0000173407.40773.17","journal-title":"Stroke"},{"key":"455_CR34","doi-asserted-by":"publisher","first-page":"269","DOI":"10.3174\/ajnr.A4088","volume":"36","author":"L Legrand","year":"2015","unstructured":"Legrand L, Tisserand M, Turc G et al (2015) Do flair vascular hyperintensities beyond the dwi lesion represent the ischemic penumbra? AJNR Am J Neuroradiol 36:269\u2013274. https:\/\/doi.org\/10.3174\/ajnr.A4088","journal-title":"AJNR Am J Neuroradiol"},{"key":"455_CR35","doi-asserted-by":"publisher","first-page":"5567","DOI":"10.1007\/s00330-019-06094-y","volume":"29","author":"L Legrand","year":"2019","unstructured":"Legrand L, Turc G, Edjlali M et al (2019) Benefit from revascularization after thrombectomy according to flair vascular hyperintensities-dwi mismatch. Eur Radiol 29:5567\u20135576. https:\/\/doi.org\/10.1007\/s00330-019-06094-y","journal-title":"Eur Radiol"},{"key":"455_CR36","doi-asserted-by":"publisher","first-page":"489","DOI":"10.1161\/STROKEAHA.119.027457","volume":"51","author":"K Wang","year":"2020","unstructured":"Wang K, Shou Q, Ma SJ et al (2020) Deep learning detection of penumbral tissue on arterial spin labeling in stroke. Stroke 51:489\u2013497. https:\/\/doi.org\/10.1161\/STROKEAHA.119.027457","journal-title":"Stroke"},{"key":"455_CR37","doi-asserted-by":"publisher","first-page":"e220882","DOI":"10.1148\/radiol.220882","volume":"307","author":"Y Yu","year":"2023","unstructured":"Yu Y, Christensen S, Ouyang J et al (2023) Predicting hypoperfusion lesion and target mismatch in stroke from diffusion-weighted mri using deep learning. Radiology 307:e220882. https:\/\/doi.org\/10.1148\/radiol.220882","journal-title":"Radiology"},{"key":"455_CR38","doi-asserted-by":"publisher","first-page":"80","DOI":"10.1186\/s12929-020-00672-9","volume":"27","author":"DP Kuo","year":"2020","unstructured":"Kuo DP, Kuo PC, Chen YC et al (2020) Machine learning-based segmentation of ischemic penumbra by using diffusion tensor metrics in a rat model. J Biomed Sci 27:80. https:\/\/doi.org\/10.1186\/s12929-020-00672-9","journal-title":"J Biomed Sci"},{"key":"455_CR39","doi-asserted-by":"publisher","unstructured":"Proskura P, Zaytsev A (2022) Effective training-time stacking for ensembling of deep neural networksProceedings of the 2022 5th International Conference on Artificial Intelligence and Pattern Recognition, pp 78\u201382. https:\/\/doi.org\/10.1145\/3573942.3573954","DOI":"10.1145\/3573942.3573954"},{"key":"455_CR40","doi-asserted-by":"publisher","first-page":"888","DOI":"10.1212\/WNL.0000000000008481","volume":"93","author":"A Vagal","year":"2019","unstructured":"Vagal A, Wintermark M, Nael K et al (2019) Automated ct perfusion imaging for acute ischemic stroke: Pearls and pitfalls for real-world use. Neurology 93:888\u2013898. https:\/\/doi.org\/10.1212\/WNL.0000000000008481","journal-title":"Neurology"},{"key":"455_CR41","doi-asserted-by":"publisher","first-page":"1330","DOI":"10.2214\/AJR.09.2845","volume":"194","author":"RM Ferreira","year":"2010","unstructured":"Ferreira RM, Lev MH, Goldmakher GV et al (2010) Arterial input function placement for accurate ct perfusion map construction in acute stroke. AJR Am J Roentgenol 194:1330\u20131336. https:\/\/doi.org\/10.2214\/AJR.09.2845","journal-title":"AJR Am J Roentgenol"},{"key":"455_CR42","doi-asserted-by":"publisher","first-page":"e0133566","DOI":"10.1371\/journal.pone.0133566","volume":"10","author":"WA Copen","year":"2015","unstructured":"Copen WA, Morais LT, Wu O et al (2015) In acute stroke, can ct perfusion-derived cerebral blood volume maps substitute for diffusion-weighted imaging in identifying the ischemic core? PLoS One 10:e0133566. https:\/\/doi.org\/10.1371\/journal.pone.0133566","journal-title":"PLoS One"},{"key":"455_CR43","doi-asserted-by":"publisher","first-page":"e0188891","DOI":"10.1371\/journal.pone.0188891","volume":"12","author":"WA Copen","year":"2017","unstructured":"Copen WA, Yoo AJ, Rost NS et al (2017) In patients with suspected acute stroke, ct perfusion-based cerebral blood flow maps cannot substitute for dwi in measuring the ischemic core. PLoS One 12:e0188891. https:\/\/doi.org\/10.1371\/journal.pone.0188891","journal-title":"PLoS One"},{"key":"455_CR44","doi-asserted-by":"publisher","first-page":"4938","DOI":"10.1038\/s41467-023-40564-8","volume":"14","author":"G Brugnara","year":"2023","unstructured":"Brugnara G, Baumgartner M, Scholze ED et al (2023) Deep-learning based detection of vessel occlusions on ct-angiography in patients with suspected acute ischemic stroke. Nat Commun 14:4938. https:\/\/doi.org\/10.1038\/s41467-023-40564-8","journal-title":"Nat Commun"},{"key":"455_CR45","doi-asserted-by":"publisher","first-page":"355","DOI":"10.1002\/jmri.26288","volume":"49","author":"RR Edelman","year":"2019","unstructured":"Edelman RR, Koktzoglou I (2019) Noncontrast mr angiography: An update. J Magn Reson Imaging 49:355\u2013373. https:\/\/doi.org\/10.1002\/jmri.26288","journal-title":"J Magn Reson Imaging"},{"key":"455_CR46","doi-asserted-by":"publisher","first-page":"1985","DOI":"10.1161\/STROKEAHA.114.005305","volume":"45","author":"K Nael","year":"2014","unstructured":"Nael K, Khan R, Choudhary G et al (2014) Six-minute magnetic resonance imaging protocol for evaluation of acute ischemic stroke: Pushing the boundaries. Stroke 45:1985\u20131991. https:\/\/doi.org\/10.1161\/STROKEAHA.114.005305","journal-title":"Stroke"},{"key":"455_CR47","doi-asserted-by":"publisher","first-page":"757","DOI":"10.1016\/j.jksuci.2023.01.014","volume":"35","author":"A Mohammed","year":"2023","unstructured":"Mohammed A, Kora R (2023) A comprehensive review on ensemble deep learning: opportunities and challenges. J King Saud Univ-Com 35:757\u2013774. https:\/\/doi.org\/10.1016\/j.jksuci.2023.01.014","journal-title":"J King Saud Univ-Com"},{"key":"455_CR48","doi-asserted-by":"publisher","first-page":"104554","DOI":"10.1016\/j.compbiomed.2021.104554","volume":"135","author":"SK Kalagotla","year":"2021","unstructured":"Kalagotla SK, Gangashetty SV, Giridhar K (2021) A novel stacking technique for prediction of diabetes. Comput Biol Med 135:104554. https:\/\/doi.org\/10.1016\/j.compbiomed.2021.104554","journal-title":"Comput Biol Med"},{"key":"455_CR49","doi-asserted-by":"publisher","unstructured":"Odegua R (2019) An empirical study of ensemble techniques (bagging, boosting and stacking)Proc. Conf.: Deep Learn. IndabaXAt. https:\/\/doi.org\/10.13140\/RG.2.2.35180.10882","DOI":"10.13140\/RG.2.2.35180.10882"},{"key":"455_CR50","doi-asserted-by":"publisher","unstructured":"Ahmad MA, Eckert C, Teredesai A (2018) Interpretable machine learning in healthcare. Proceedings of the 2018 ACM international conference on bioinformatics, computational biology, and health informatics, pp 559\u2013560. https:\/\/doi.org\/10.1145\/3233547.3233667","DOI":"10.1145\/3233547.3233667"},{"key":"455_CR51","doi-asserted-by":"publisher","unstructured":"Alfi IA, Rahman MM, Shorfuzzaman M et al (2022) A non-invasive interpretable diagnosis of melanoma skin cancer using deep learning and ensemble stacking of machine learning models. Diagnostics (Basel) 12. https:\/\/doi.org\/10.3390\/diagnostics12030726","DOI":"10.3390\/diagnostics12030726"},{"key":"455_CR52","doi-asserted-by":"publisher","first-page":"975855","DOI":"10.3389\/fphar.2022.975855","volume":"13","author":"X Zhu","year":"2022","unstructured":"Zhu X, Hu J, Xiao T et al (2022) An interpretable stacking ensemble learning framework based on multi-dimensional data for real-time prediction of drug concentration: the example of olanzapine. Front Pharmacol 13:975855. https:\/\/doi.org\/10.3389\/fphar.2022.975855","journal-title":"Front Pharmacol"},{"key":"455_CR53","doi-asserted-by":"publisher","first-page":"10256","DOI":"10.1038\/s41598-023-35476-y","volume":"13","author":"PW Khan","year":"2023","unstructured":"Khan PW, Byun YC, Jeong OR (2023) A stacking ensemble classifier-based machine learning model for classifying pollution sources on photovoltaic panels. Sci Rep 13:10256. https:\/\/doi.org\/10.1038\/s41598-023-35476-y","journal-title":"Sci Rep"},{"key":"455_CR54","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1186\/s12911-023-02159-7","volume":"23","author":"X Lu","year":"2023","unstructured":"Lu X, Qiu H (2023) Explainable prediction of daily hospitalizations for cerebrovascular disease using stacked ensemble learning. BMC Med Inform Decis Mak 23:59. https:\/\/doi.org\/10.1186\/s12911-023-02159-7","journal-title":"BMC Med Inform Decis Mak"},{"key":"455_CR55","doi-asserted-by":"publisher","first-page":"150","DOI":"10.1016\/j.dss.2015.04.003","volume":"74","author":"HM Zolbanin","year":"2015","unstructured":"Zolbanin HM, Delen D, Zadeh AH (2015) Predicting overall survivability in comorbidity of cancers: a data mining approach. Decis Support Syst 74:150\u2013161. https:\/\/doi.org\/10.1016\/j.dss.2015.04.003","journal-title":"Decis Support Syst"},{"key":"455_CR56","doi-asserted-by":"publisher","first-page":"515","DOI":"10.1016\/j.jstrokecerebrovasdis.2015.10.033","volume":"25","author":"M Lopez-Mejia","year":"2016","unstructured":"Lopez-Mejia M, Roldan-Valadez E (2016) Comparisons of apparent diffusion coefficient values in penumbra, infarct, and normal brain regions in acute ischemic stroke: confirmatory data using bootstrap confidence intervals, analysis of variance, and analysis of means. J Stroke Cerebrovasc Dis 25:515\u2013522. https:\/\/doi.org\/10.1016\/j.jstrokecerebrovasdis.2015.10.033","journal-title":"J Stroke Cerebrovasc Dis"},{"key":"455_CR57","doi-asserted-by":"publisher","first-page":"2486","DOI":"10.1161\/hs1101.098331","volume":"32","author":"C Oppenheim","year":"2001","unstructured":"Oppenheim C, Grandin C, Samson Y et al (2001) Is there an apparent diffusion coefficient threshold in predicting tissue viability in hyperacute stroke? Stroke 32:2486\u20132491. https:\/\/doi.org\/10.1161\/hs1101.098331","journal-title":"Stroke"},{"key":"455_CR58","doi-asserted-by":"publisher","first-page":"75","DOI":"10.3348\/kjr.2005.6.2.75","volume":"6","author":"WJ Moon","year":"2005","unstructured":"Moon WJ, Na DG, Ryoo JW et al (2005) Assessment of tissue viability using diffusion- and perfusion-weighted mri in hyperacute stroke. Korean J Radiol 6:75\u201381. https:\/\/doi.org\/10.3348\/kjr.2005.6.2.75","journal-title":"Korean J Radiol"},{"key":"455_CR59","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1016\/j.brainres.2012.01.043","volume":"1445","author":"M Pitkonen","year":"2012","unstructured":"Pitkonen M, Abo-Ramadan U, Marinkovic I et al (2012) Long-term evolution of diffusion tensor indices after temporary experimental ischemic stroke in rats. Brain Res 1445:103\u2013110. https:\/\/doi.org\/10.1016\/j.brainres.2012.01.043","journal-title":"Brain Res"},{"key":"455_CR60","doi-asserted-by":"publisher","first-page":"1517","DOI":"10.1161\/01.str.0000016973.80180.7b","volume":"33","author":"HA Green","year":"2002","unstructured":"Green HA, Pena A, Price CJ et al (2002) Increased anisotropy in acute stroke: a possible explanation. Stroke 33:1517\u20131521. https:\/\/doi.org\/10.1161\/01.str.0000016973.80180.7b","journal-title":"Stroke"},{"key":"455_CR61","doi-asserted-by":"publisher","first-page":"e2001494","DOI":"10.1371\/journal.pbio.2001494","volume":"15","author":"Y Abe","year":"2017","unstructured":"Abe Y, Tsurugizawa T, Le Bihan D (2017) Water diffusion closely reveals neural activity status in rat brain loci affected by anesthesia. PLoS Biol 15:e2001494. https:\/\/doi.org\/10.1371\/journal.pbio.2001494","journal-title":"PLoS Biol"},{"key":"455_CR62","doi-asserted-by":"publisher","first-page":"328","DOI":"10.1159\/000084691","volume":"19","author":"CS Rivers","year":"2005","unstructured":"Rivers CS, Wardlaw JM (2005) What has diffusion imaging in animals told us about diffusion imaging in patients with ischaemic stroke? Cerebrovasc Dis 19:328\u2013336. https:\/\/doi.org\/10.1159\/000084691","journal-title":"Cerebrovasc Dis"},{"key":"455_CR63","doi-asserted-by":"publisher","first-page":"1090","DOI":"10.1002\/mrm.26722","volume":"79","author":"M Behroozi","year":"2018","unstructured":"Behroozi M, Chwiesko C, Strockens F et al (2018) In vivo measurement of T1 and T2 relaxation times in awake pigeon and rat brains at 7T. Magn Reson Med 79:1090\u20131100. https:\/\/doi.org\/10.1002\/mrm.26722","journal-title":"Magn Reson Med"},{"key":"455_CR64","doi-asserted-by":"publisher","first-page":"1877","DOI":"10.1016\/j.ejrad.2011.04.074","volume":"81","author":"A Zolal","year":"2012","unstructured":"Zolal A, Sames M, Burian M et al (2012) The effect of a gadolinium-based contrast agent on diffusion tensor imaging. Eur J Radiol 81:1877\u20131882. https:\/\/doi.org\/10.1016\/j.ejrad.2011.04.074","journal-title":"Eur J Radiol"}],"container-title":["European Radiology Experimental"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s41747-024-00455-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s41747-024-00455-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s41747-024-00455-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,15]],"date-time":"2024-05-15T00:03:36Z","timestamp":1715731416000},"score":1,"resource":{"primary":{"URL":"https:\/\/eurradiolexp.springeropen.com\/articles\/10.1186\/s41747-024-00455-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,15]]},"references-count":64,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2024,12]]}},"alternative-id":["455"],"URL":"https:\/\/doi.org\/10.1186\/s41747-024-00455-z","relation":{},"ISSN":["2509-9280"],"issn-type":[{"type":"electronic","value":"2509-9280"}],"subject":[],"published":{"date-parts":[[2024,5,15]]},"assertion":[{"value":"20 December 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 March 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 May 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Approval from the institutional animal care committee was obtained (approval No: LAC-2022\u20130069).","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"The authors declare that they have no competing interests.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"59"}}